Exploratory analysis of monkeypox data using Plotly, Pandas, Wordcloud, etc.

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly.graph_objects as go
import seaborn as sns
import plotly.express as px
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

data = pd.read_csv("https://raw.githubusercontent.com/globaldothealth/monkeypox/main/latest.csv",low_memory=False)

print(data.shape)

(39001, 36)

data.head()

	ID	Status	Location	City	Country	Country_ISO3	Age	Gender	Date_onset	Date_confirmation	...	Source	Source_II	Source_III	Source_IV	Source_V	Source_VI	Source_VII	Date_entry	Date_death	Date_last_modified
0	N1	confirmed	Guy's and St Thomas Hospital London	London	England	GBR	NaN	NaN	2022-04-29	2022-05-06	...	https://www.gov.uk/government/news/monkeypox-c...	https://www.who.int/emergencies/disease-outbre...	NaN	NaN	NaN	NaN	NaN	2022-05-18	NaN	2022-05-18
1	N2	confirmed	Guy's and St Thomas Hospital London	London	England	GBR	NaN	NaN	2022-05-05	2022-05-12	...	https://www.gov.uk/government/news/monkeypox-c...	NaN	NaN	NaN	NaN	NaN	NaN	2022-05-18	NaN	2022-05-18
2	N3	confirmed	London	London	England	GBR	NaN	NaN	2022-04-30	2022-05-13	...	https://www.gov.uk/government/news/monkeypox-c...	NaN	NaN	NaN	NaN	NaN	NaN	2022-05-18	NaN	2022-05-18
3	N4	confirmed	London	London	England	GBR	NaN	male	NaN	2022-05-15	...	https://www.gov.uk/government/news/monkeypox-c...	NaN	NaN	NaN	NaN	NaN	NaN	2022-05-18	NaN	2022-05-18
4	N5	confirmed	London	London	England	GBR	NaN	male	NaN	2022-05-15	...	https://www.gov.uk/government/news/monkeypox-c...	NaN	NaN	NaN	NaN	NaN	NaN	2022-05-18	NaN	2022-05-18

5 rows × 36 columns

Missingness of the data

• data.isna().sum(): count the number of missing observations per column in the datset

# Create dataframe counting NaN values per column
nan_df = pd.DataFrame(data.isna().sum()).reset_index()
nan_df.columns  = ['Column', 'NaN_Count']
nan_df['NaN_Count'] = nan_df['NaN_Count'].astype('int')
nan_df['NaN_%'] = round(nan_df['NaN_Count']/data.shape[0] * 100,1)
nan_df['Type']  = 'Missingness'
nan_df.sort_values('NaN_%', inplace = True)

# Add completeness: 1- missingness%
for i in range(nan_df.shape[0]):
    complete_df = pd.DataFrame([nan_df.loc[i,'Column'],data.shape[0] - nan_df.loc[i,'NaN_Count'],100 - nan_df.loc[i,'NaN_%'], 'Completeness']).T
    complete_df.columns  = ['Column','NaN_Count','NaN_%','Type']
    complete_df['NaN_%'] = complete_df['NaN_%'].astype('int')
    complete_df['NaN_Count'] = complete_df['NaN_Count'].astype('int')
    nan_df = nan_df.append(complete_df, sort = True)

nan_df.head()  

	Column	NaN_%	NaN_Count	Type
0	ID	0.0	0	Missingness
33	Date_entry	0.0	0	Missingness
26	Source	0.0	0	Missingness
5	Country_ISO3	0.0	0	Missingness
35	Date_last_modified	0.0	0	Missingness

# Missingness Plot
fig = px.bar(nan_df,
             x = 'Column',
             y = 'NaN_%',
             title = 'Missingness within this Dataset',
             color = 'Type',
             template = 'plotly_dark',
             opacity = 0.6,
             width = 800,
             height = 450,
             color_discrete_sequence = ['#dbdbdb','#38cae0']
            )
fig.update_yaxes(title = 'Percentage of NaNs')
fig.update_xaxes(title = 'Column Name')

plt.show(block = False)

fig.show()

Geographical distribution of confirmed cases

• confirmed_data[['Country_ISO3','ID']].groupby('Country_ISO3').agg('count').reset_index() : count the number of confirmed cases by country

# we can pull confirmed cases
confirmed_data = data.loc[data["Status"] == "confirmed"]
data_df = confirmed_data[['Country_ISO3','ID']].groupby('Country_ISO3').agg('count').reset_index()
data_df.rename({'ID':'Total'}, axis = 1, inplace = True)
data_df.head()## Country_ISO3 are three-letter country codes

	Country_ISO3	Total
0	AND	4
1	ARE	16
2	ARG	49
3	AUS	71
4	AUT	198

fig = px.choropleth(data_df,
                    locations = "Country_ISO3",
                    color = "Total",
                    hover_name = "Country_ISO3",
                    color_continuous_scale = "peach",
                    projection = 'orthographic',
                    template = 'plotly_dark',
                    title = 'Geographical Distribution of Confirmed Monkeypox Cases<br><sub>Natural Projection</sub>',
                    height = 450,
                    width = 800,
                   )

fig.update_geos(lataxis_showgrid = True,
                lonaxis_showgrid = True,
                showcountries = True,
               )

fig.update_geos(lataxis = {'gridcolor':'#222222'},
                lonaxis = {'gridcolor':'#222222'},
               )

plt.show(block = False)

fig.show()

fig = px.scatter_geo(data_df, locations="Country_ISO3", 
                     color="Total",
                     hover_name="Country_ISO3", 
                     size="Total",
                     title = 'Geographical Distribution of Confirmed Monkeypox Cases using Bubble Maps',
                     projection="natural earth",
                     color_continuous_scale = ['#06FF00','#FFE400','#FF8E00','#FF1700'],                
                     template = 'plotly_dark',
                     height = 450,
                     width = 800,
                    )
plt.show(block = False)

fig.show()

fig = px.choropleth(data_df,
                    locations = "Country_ISO3",
                    color = "Total",
                    hover_name = "Country_ISO3",
                    scope = 'europe',
                    color_continuous_scale = "peach",
                    template = 'plotly_dark',
                    title = 'Distribution of Confirmed Monkeypox Cases<br><sub>European </sub>',
                    height = 450,
                    width = 800,
                   )

fig.update_geos(lataxis_showgrid = True,
                lonaxis_showgrid = True,
                showcountries = True,
                showsubunits = True,
               )

fig.update_geos(lataxis = {'gridcolor':'#222222'},
                lonaxis = {'gridcolor':'#222222'},
               )
plt.show(block = False)

fig.show()

Number of confirmed cases changes over time

• data[['Date_confirmation','ID']].groupby('Date_confirmation').agg('count').reset_index(): count the number of confirmed cases by date

acumulated_df = data[['Date_confirmation','ID']].groupby('Date_confirmation').agg('count').reset_index()
acumulated_df['Accumulated Cases'] = acumulated_df['ID'].cumsum()
acumulated_df.rename({'ID':'Count'}, axis = 1, inplace = True)
acumulated_df.head()

	Date_confirmation	Count	Accumulated Cases
0	2022-01-31	2	2
1	2022-02-17	3	5
2	2022-02-28	1	6
3	2022-03-04	2	8
4	2022-03-31	6	14

fig = px.bar(acumulated_df,
             x = 'Date_confirmation',
             y = 'Count',
             text = 'Count',
             color = 'Count',
             opacity = 0.9,
             title = 'Number of Confirmed Cases by Date',
             color_continuous_scale = ['#bbbbbb','#38cae0'],
             template = 'plotly_dark',
             hover_data = ['Count'],#The hover_name property controls which column is displayed in bold as the tooltip title.
             color_continuous_midpoint = 1000,
             height = 450,
             width = 800,
            )
avg_returns = acumulated_df['Count'].mean()
avg_returns_color = '#bbbbbb'
fig.add_hline(y = avg_returns,
              line_width = 1.,
              line_dash = "dot",
              opacity = 0.7,
              fillcolor = avg_returns_color,
              annotation_text = "Average: " + str(round(avg_returns,1)) + ' cases per day', 
              annotation_position = "bottom right",
              annotation_font_size = 10,
              annotation_font_color = "white",
              line_color = avg_returns_color,
             )
fig.update_xaxes(showticklabels = True,
                 dtick = "M1",
                 tickformat = "%b %Y",
                )
fig.update_yaxes(title = 'Confirmed Cases')
fig.update_xaxes(title = 'Date')

plt.show(block = False)

fig.show()

Number of confirmed cases by days

• .reindex(cat): reorder the data by the specific category
• .to_datetime(): convert argument to datetime
• .day_name(): return the day names

cats = [ 'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
data_sort = pd.to_datetime(confirmed_data['Date_confirmation']).dt.day_name().value_counts().reindex(cats)
data_sort.head()

Monday       7459
Tuesday      7932
Wednesday    5021
Thursday     6701
Friday       7328
Name: Date_confirmation, dtype: int64

fig = px.bar(data_sort,
             opacity = 0.9,
             title = 'Number of Confirmed Cases by Days',
             color_continuous_scale = ['#bbbbbb','#38cae0'],
             template = 'plotly_dark',
             #The hover_name property controls which column is displayed in bold as the tooltip title.
             color_continuous_midpoint = 0,
             height = 450,
             width = 800,
            )

plt.show(block = False)

fig.show()

Identify the most common symptoms associated with monkeypox

data.fillna("",inplace=True) # replace NaN by ""
def function(train):   
    comment_words = ""
    for i in train:
        val = str(i)
        tokens = val.split()
        for k in range(len(tokens)):
            tokens[k] = tokens[k].lower()
        comment_words += " ".join(tokens)+" "
    return comment_words

def plot_wordcloud(data):    
    from wordcloud import WordCloud, STOPWORDS
    stopwords = set(STOPWORDS)
    comment_words = function(data)
    wordcloud = WordCloud(width = 800, 
                          height = 450,
                          contour_color='#023075',
                          background_color ='black',
                          colormap='autumn',
                          min_font_size = 20,
                          collocations=False).generate(comment_words)
    # plot the WordCloud image 
    plt.figure(figsize = (16, 9),
           facecolor = None)
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.tight_layout(pad = 0)

plot_wordcloud(data['Symptoms'])

temp_df = pd.DataFrame(data.loc[data['Symptoms'] != "",'Symptoms'].value_counts()).reset_index()
#if count=1 belongs to "other" category and count the total number
temp_df = temp_df.append(pd.DataFrame({'index':'Other', 'Symptoms':temp_df.loc[temp_df['Symptoms'] < 2]['Symptoms'].sum()},index = [0]))
temp_df = temp_df.loc[temp_df['Symptoms'] > 1]


fig = go.Figure(data = [go.Pie(labels = temp_df['index'],
                               values = temp_df['Symptoms'],
                               hole = .75,
                               #title = '% of Symptons',
                               marker_colors =px.colors.sequential.Agsunset,
                              )])
fig.update_layout(
    title_text = "Majorly affecting symptoms",
    template = 'plotly_dark',
    width = 800,
    height = 450,
    annotations = [dict(text = 'Symptoms',
                      x = 0.5,
                      y = 0.5,
                      font_size = 20,
                      showarrow = False
                     )])
plt.show(block = False)

fig.show()

Are patient characteristics (e.g., gender) associated with monkeypox?

data.loc[data['Gender'] == 'male','Gender'] = 'Male'
data.loc[data['Gender'] == 'male ','Gender'] = 'Male'
data.loc[data['Gender'] == 'female','Gender'] = 'Female'
data.loc[data['Gender'] == 'female ','Gender'] = 'Female'
filtered_df = data.loc[data['Status'] == 'confirmed']
filtered_df = filtered_df.loc[filtered_df['Gender'] != ""]

temp_df = filtered_df[['Gender','ID']].groupby('Gender').agg('count').reset_index()
temp_df.rename({'ID':'Count'}, axis = 1, inplace = True)
temp_df['Percentage'] = (temp_df['Count']/temp_df['Count'].sum() * 100).round(2)
temp_df['Percentage'] = temp_df['Percentage'].astype('str') + '%'
n = temp_df['Count'].sum()
n_total = data.shape[0]
fig = px.bar(temp_df,
             y = 'Gender',
             x = 'Count',
             title = 'Distribution of Sex Among Confirmed Cases<br><sub>Calculated on a sample of {} out of {} observations in the dataset</sub>'.format(n,n_total),
             color = 'Gender',
             text = 'Percentage',
             template = 'plotly_dark',
             opacity = 0.8,
             height = 450,
             width = 800,
             color_discrete_sequence = ['#dbdbdb','#38cae0']
            )
fig.update_yaxes(title = 'Count of Occurences')
fig.update_xaxes(title = 'Sex')
plt.show(block = False)

fig.show()